mlsanityData to 14 Oct 2026

OctNet: Learning Deep 3D Representations at High Resolutions

arXiv 1611.05009 ↗First posted 15 Nov 2016cs.CVcited by 342

Not on the map. Why?

Abstract (arXiv)

We present OctNet, a representation for deep learning with sparse 3D data. In contrast to existing models, our representation enables 3D convolutional networks which are both deep and high resolution. Towards this goal, we exploit the sparsity in the input data to hierarchically partition the space using a set of unbalanced octrees where each leaf node stores a pooled feature representation. This allows to focus memory allocation and computation to the relevant dense regions and enables deeper networks without compromising resolution. We demonstrate the utility of our OctNet representation by analyzing the impact of resolution on several 3D tasks including 3D object classification, orientation estimation and point cloud labeling.

Key facts. Cited by 342 papers in the map (data through 14 Oct 2026). First posted on arXiv 15 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 113; 2022: 76; 2023: 70; 2024: 43; 2025: 20; 2026: 20.

342 papers.

Sort:

By area:

  1. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  2. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  3. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 460
  4. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 458
  5. 2021Advances in Neural Renderingcited by 365
  6. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  7. 2022Language-Grounded Indoor 3D Semantic Segmentation in the Wildcited by 246
  8. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  9. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  10. 2022SoftGroup for 3D Instance Segmentation on Point Cloudscited by 200
  11. 2024Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoningcited by 175
  12. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
38 more
  1. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  2. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  3. 2021InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referringcited by 141
  4. 2021Hierarchical Aggregation for 3D Instance Segmentationcited by 127
  5. 2021NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenescited by 119
  6. 2021A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representationcited by 114
  7. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 109
  8. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 103
  9. 2024DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Modelscited by 98
  10. 2021Bidirectional Projection Network for Cross Dimension Scene Understandingcited by 95
  11. 20223DILG: Irregular Latent Grids for 3D Generative Modelingcited by 93
  12. 2022POCO: Point Convolution for Surface Reconstructioncited by 92
  13. 2021One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentationcited by 89
  14. 2021Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentationcited by 87
  15. 2021A comprehensive survey on point cloud registrationcited by 84
  16. 2022Surface Representation for Point Cloudscited by 84
  17. 20213D Semantic Scene Completion: a Surveycited by 74
  18. 2022P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Promptingcited by 74
  19. 2023FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformercited by 73
  20. 2021Understanding Pooling in Graph Neural Networkscited by 69
  21. 2023InfiniCity: Infinite-Scale City Synthesiscited by 68
  22. 2021Deep Implicit Moving Least-Squares Functions for 3D Reconstructioncited by 67
  23. 2025CAD-Llama: Leveraging Large Language Models for Computer-Aided Design Parametric 3D Model Generationcited by 67
  24. 2021Multi-Modal 3D Object Detection in Autonomous Driving: a Surveycited by 63
  25. 2021Adaptive Graph Convolution for Point Cloud Analysiscited by 60
  26. 2021Learning 3D Semantic Segmentation with only 2D Image Supervisioncited by 60
  27. 2021SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networkscited by 59
  28. 2022AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstructioncited by 59
  29. 2021PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysiscited by 58
  30. 2022OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compressioncited by 58
  31. 2023Efficient 3D Semantic Segmentation with Superpoint Transformercited by 57
  32. 2021Semantics for Robotic Mapping, Perception and Interaction: A Surveycited by 56
  33. 2022Contrastive Boundary Learning for Point Cloud Segmentationcited by 56
  34. 2021Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Cloudscited by 55
  35. 2022Few-View Object Reconstruction with Unknown Categories and Camera Posescited by 53
  36. 2021Learning Semantic Segmentation of Large-Scale Point Clouds with Random Samplingcited by 51
  37. 2021CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsingcited by 51
  38. 20213D-to-2D Distillation for Indoor Scene Parsingcited by 48

50 most cited of 342 All 342 (JSON)